Abstract
dc:description.abstractThis dissertation describes methods for enhancing generative models with either added controllability or expressiveness of uncertainty, demonstrating how a strong prior enables both features. One general approach is to introduce new architectures or training objectives. However, current trends towards massive upscaling of model size, training data, and computational resources can make retraining or fine-tuning difficult and expensive. Thus, another approach is to build upon existing pre-trained models. We consider both types of approaches with an emphasis on the latter. We first tackle the tasks of controllable image synthesis and uncertainty estimation through training-based methods and then switch focus towards computationally-efficient methods that do not require direct updates to the base model's parameters. We conclude by discussing future directions based on the insights from our findings.
Degree
thesis:*- Level thesis:degree_level
- Doctoral
- Department dc:contributor.department
- Interactive Computing
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Ham, Cusuh
- Advisor dc:contributor.advisor
-
- Hays, James
- Committee members dc:contributor.committeemember
-
- Hoffman, Judy
- Kira, Zsolt
- Shi, Humphrey
- Zhu, Jun-Yan
Subjects
dc:subject × 5Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/73167